GA-Optimized ANN for Modeling of UWB Filters

This paper introduces the genetic algorithm (GA) into the artificial neural network (ANN) for the parametric modeling of ultra-wideband bandpass filters. With the optimization of thresholds and weights in ANN, GA speeds up the convergence of ANN training. The trained ANN, instead of the time-consuming full-wave simulation, is repeatedly called in the design process, leading to an efficient solution.